Spaces:
Sleeping
Sleeping
Update space.yaml
Browse files- space.yaml +22 -1
space.yaml
CHANGED
|
@@ -1,3 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
sdk: gradio
|
| 2 |
-
|
|
|
|
| 3 |
app_file: app.py
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
title: Chat with DeepSeek Coder 1.3B
|
| 2 |
+
emoji: 💬
|
| 3 |
+
colorFrom: blue
|
| 4 |
+
colorTo: indigo
|
| 5 |
sdk: gradio
|
| 6 |
+
sdk_version: 4.25.0 # Or your target Gradio version
|
| 7 |
+
python_version: "3.10" # Or "3.9", "3.11", etc.
|
| 8 |
app_file: app.py
|
| 9 |
+
pinned: false
|
| 10 |
+
# If you were using secrets (like HF_TOKEN for an API):
|
| 11 |
+
# secrets:
|
| 12 |
+
# - HF_TOKEN
|
| 13 |
+
# If you needed persistent storage:
|
| 14 |
+
# persistent_storage:
|
| 15 |
+
# - path: /data
|
| 16 |
+
# mount_to: /home/user/app/data # Example mount path
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# Chat with Quantized DeepSeek Coder 1.3B
|
| 20 |
+
|
| 21 |
+
This is a Gradio application that allows you to chat with the `deepseek-ai/deepseek-coder-1.3b-instruct` model.
|
| 22 |
+
The model is loaded directly within the Space. If a GPU is available, 8-bit quantization is attempted; otherwise, the model is loaded on CPU in its native precision.
|
| 23 |
+
|
| 24 |
+
**Note:** Model loading can take a few minutes, especially on the first run or after a rebuild.
|